Capture Career Notes

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses the API-key requirement and its failure mode, the 409 refusal condition tied to another tool, the fact an LLM call is made and may create a new entity, that output is unapproved drafts surfaced at /career, and that content is unverified user words. That is exactly the behavior an agent needs before invoking a mutating, non-idempotent tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and state, then prerequisites and the alternative tool. Dense with parenthetical asides ("(with none set it returns an error)", "(get_setup_status)") that add value but make it slightly cluttered; still no wasted sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter mutating tool with no output schema, it covers auth, error/409 behavior, draft lifecycle, where approval happens, and the sibling alternative. Nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry parameter meaning: it explains entity_id's semantics (force placement rather than letting AI match) and characterizes text as free-text news stored verbatim as the user's own words. The text parameter's expected granularity (a news item vs. a full bio) is only loosely implied, keeping it short of a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

"Capture free-text career news into DRAFT points" is a specific verb plus resource plus state (draft), and the description explicitly contrasts it with kb_add_points (no LLM call) and kb_edit_point/kb_approve_points territory. An agent can distinguish it from the many sibling kb_* tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives when-to-use (free-text capture that needs AI entity matching), when-not (use kb_add_points for bullets the caller already wrote), a pre-condition (get_setup_status writer setting, else 409), and an override path (pass entity_id to force placement). No inference is required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.